{"id":"W2979544332","doi":"10.2196/14806","title":"A Deep Learning Approach for Managing Medical Consumable Materials in Intensive Care Units via Convolutional Neural Networks: Technical Proof-of-Concept Study","year":2019,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Digital Imaging for Blood Diseases","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Consumables; Context (archaeology); Convolutional neural network; Deep learning; Documentation; Intensive care; Identification (biology); Artificial intelligence; Patient safety; Machine learning; Health care; Medicine","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000654603,0.0002465787,0.0005522261,0.0002078877,0.00007054528,0.0001577949,0.001274854,0.0001901331,0.00004533292],"category_scores_gemma":[0.001146809,0.0002138451,0.00007475951,0.0006277553,0.0003144696,0.0009868009,0.0008720156,0.0004761924,0.00000642059],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008294577,"about_ca_system_score_gemma":0.0003367607,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001487085,"about_ca_topic_score_gemma":0.000005062968,"domain_scores_codex":[0.9966394,0.0001110463,0.001090596,0.0002657118,0.001339354,0.0005538458],"domain_scores_gemma":[0.9978815,0.0003572182,0.0003126631,0.000398687,0.0006867785,0.0003631704],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008117614,0.004403241,0.06024242,0.007185818,0.000726849,0.0003729001,0.1218113,0.1610265,0.00002499221,0.03380794,0.003636809,0.6059495],"study_design_scores_gemma":[0.002236649,0.0004098073,0.0004255999,0.0002252911,0.00001684577,0.00007250866,0.01120827,0.9848281,0.00006440015,0.0001618509,0.00009223251,0.0002583975],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3134374,0.0003729048,0.6802354,0.0002263422,0.0005715533,0.0035044,0.00001302291,0.0003079062,0.00133106],"genre_scores_gemma":[0.9934009,0.000001644913,0.005394824,0.0007248874,0.00005267103,0.0002599907,0.0001267199,0.00001743107,0.00002097014],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8238016,"threshold_uncertainty_score":0.8720351,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01633197118029734,"score_gpt":0.2757579147474021,"score_spread":0.2594259435671048,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}